{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TBPK6TQZC6OZIZQRA3HVAYMVLJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5d88640e2835e629048393897bf189e37b8cb307a6e00fd8b32a4d1b917931a6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-16T04:01:50Z","title_canon_sha256":"4047f2b3e26bbbc70af202e114313c9b43eafb535465d14c16754cf96425c440"},"schema_version":"1.0","source":{"id":"2403.10798","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.10798","created_at":"2026-07-05T11:28:58Z"},{"alias_kind":"arxiv_version","alias_value":"2403.10798v2","created_at":"2026-07-05T11:28:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10798","created_at":"2026-07-05T11:28:58Z"},{"alias_kind":"pith_short_12","alias_value":"TBPK6TQZC6OZ","created_at":"2026-07-05T11:28:58Z"},{"alias_kind":"pith_short_16","alias_value":"TBPK6TQZC6OZIZQR","created_at":"2026-07-05T11:28:58Z"},{"alias_kind":"pith_short_8","alias_value":"TBPK6TQZ","created_at":"2026-07-05T11:28:58Z"}],"graph_snapshots":[{"event_id":"sha256:731a080b82239e637678cb66ae86bd490d619db8e5df45969cc49b6ae019a994","target":"graph","created_at":"2026-07-05T11:28:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2403.10798/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-augmented generation (RAG) with large language models (LLMs) plays a crucial role in question answering, as LLMs possess limited knowledge and are not updated with continuously growing information. Most recent work on RAG has focused primarily on text-based or large-image retrieval, which constrains the broader application of RAG models. We recognize that object-level retrieval is essential for addressing questions that extend beyond image content. To tackle this issue, we propose a task of object retrieval for visual question answering with outside knowledge (OR-OK-VQA), aimed to ex","authors_text":"Jiale Fu, Lihui Cen, Linna Zhang, Shichao Kan, Yigang Cen, Yixiong Liang, Yuhai Deng, Zhe Qu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-16T04:01:50Z","title":"Object Retrieval for Visual Question Answering with Outside Knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10798","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b0e716b7b435ef350ca0e96304ceffe0a35ef438762f2ad4bb0cd0a2d36e5314","target":"record","created_at":"2026-07-05T11:28:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5d88640e2835e629048393897bf189e37b8cb307a6e00fd8b32a4d1b917931a6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-16T04:01:50Z","title_canon_sha256":"4047f2b3e26bbbc70af202e114313c9b43eafb535465d14c16754cf96425c440"},"schema_version":"1.0","source":{"id":"2403.10798","kind":"arxiv","version":2}},"canonical_sha256":"985eaf4e19179d94661106cf5061955a5689c8a14300034275bb914ea6ef29eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"985eaf4e19179d94661106cf5061955a5689c8a14300034275bb914ea6ef29eb","first_computed_at":"2026-07-05T11:28:58.419357Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:28:58.419357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4YAoZJFyqYyhO1mQ4TI3rwkzSzysmTfoviwZaSwWP5HTntL7mJzdbwJzt2Y/+AuoL2+WBcAwi+lCVpX3kGtiAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:28:58.419883Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.10798","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b0e716b7b435ef350ca0e96304ceffe0a35ef438762f2ad4bb0cd0a2d36e5314","sha256:731a080b82239e637678cb66ae86bd490d619db8e5df45969cc49b6ae019a994"],"state_sha256":"e00048b52d62a8540272c5dff81f709155c8c2094e83ed5058476fca9a7d86b8"}